Web applications are increasingly used in critical domains such as education, finance, and e-commerce. This highlights the need to ensure their failure-free performance. One effective method for evaluating failure-free performance is web form testing, where defining effective test scenarios is key to a complete and accurate evaluation. A core aspect of this process involves filling form fields with suitable values to create effective test cases. However, manually generating these values is time-consuming and prone to errors. To address this, various tools have been developed to assist testers. With the appearance of large language models (LLMs), a new generation of tools seeks to handle this task more intelligently. Although many LLM-based tools have been introduced, as these models typically rely on cloud infrastructure, their use in testing confidential web forms raises concerns about unintended data leakage and breaches of confidentiality. This paper introduces a privacy-preserving recommender that operates locally using a large language model. The tool assists testers in web form testing by suggesting effective field values. This tool analyzes the HTML structure of forms, detects input types, and extracts constraints based on each field’s type and contextual content, guiding proper field filling. A comparative evaluation with the T5-GPT approach on five web apps shows comparable performance (63 vs. 64 detected forms), with our local approach excelling in privacy preservation by avoiding external dependencies. Real-world testing on ten Persian- language websites yields high metrics: 92.9% accuracy, 94.4% precision, and 98% recall in field detection and value generation. These results demonstrate that the proposed approach delivers high accuracy in input generation and yields fewer failures. Overall, the study confirms the tool’s effectiveness in locally filling web forms while preserving privacy, with robust performance across diverse, real-world UI contexts, including non-English languages.

Keywords